<p id="isPasted"><em>This article is based on a webinar from Dr. Dave Garrett, Chief Architect and head of engineer at Syntiant Corporation. He&rsquo;s a technical expert in building machine learning (ML) architectures in silicon and deploying ML solutions. In the webinar, hosted by SemiWiki, Dr. Garrett demonstrated how to successfully deploy edge AI neural networks using the Syntiant&reg; ultra-low-power Neural Decision Processors&trade; (NDP).&nbsp;</em></p><p><em>These NDPs sense, analyze and autonomously act to allow mission-critical and time-sensitive decisions to be made faster, more reliably, with minimal power consumption while offering greater privacy at the edge of the network. We&rsquo;ve summarized the core takeaways of the webinar below.&nbsp;</em></p><h2>Deep Learning Enables Significant Reduction in False Alarm Events</h2><p>False alarms on home security systems are the customers&rsquo; single largest complaint. According to recent studies, false alarms are the number one reason why people don&rsquo;t actively use their installed home security systems. In these hardwired systems, there is no discerning and nuanced decision-making - they are either triggered or not. &nbsp;</p><p>Syntiant&rsquo;s solutions for home security applications are based on deep learning algorithms and aim to emulate the natural decision-making response of a person who can hear and sense an outcome, and make a determination about the underlying cause and event. Today, Syntiant offers three solutions for security applications, with the aim to expand in the future: &nbsp;person detection (vision), window-break acoustic event detection, and door/window motion detection. For each application, the Neural Decision Processor<em>&trade;</em> is paired with a standard, low cost, sensor, and trained to detect the occurrence of a specific event, making these solutions turnkey and ready for deployment.&nbsp;</p><ol><li><h3><strong>Person Detection: NDP200 and Low-cost Camera</strong></h3><br>Traditional home security systems use passive infrared sensors to detect the presence of a moving object. these sensors have no decision-making ability and rely on a single threshold, making them prone to false alarms: a god, a car, or even wind rustling the trees can trigger a &#39;&#39;person detect&#39;&#39; event.<br>The Syntiant approach is completely different.: using a basic, low-resolution camera, Syntiant&#39;s NDP200 processor is trained to detect the presence of a person only and disregard all other objects. To allow the consumer security solutions to be installed in the most convenient and meaningful locations, many of these devices are compact and battery-operated. NDP200 is offer is a 5mmx5mm package and consumes less than 1mW of when used as an always-on, person detect processor.&nbsp;</li><li><h3><strong>Window-Break Acoustic Event Detection: NDP120 and Microphone</strong></h3><strong><br></strong>The second solution that Syntiant provides for security applications is to detect the sound of a window breaking. Just as with person detection, detecting the sound of a glass breaking is prone to false detects or missed detections. Syntiant&rsquo;s NDP120 processor, trained with Syntiant&rsquo;s own generated data models is exceptionally adept at distinguishing the sound of a window breaking from other household acoustic events. &nbsp;The same processor, offered in a compact 3.1mmx2.5mm package, can also be programmed to trigger other specific acoustic events such as a smoke or fire alarms, alerting homeowners and security companies of a potential fire when no one is home.&nbsp;</li><li><h3>Motion Detection: NDP120 and Gyroscope</h3><br>The third Syntiant solution leverages the output of a six or nine-axis motion detector to determine events at the home&rsquo;s entry points. For example, the system can be trained to detect the jiggling of a doorknob.</li></ol><h2>Syntiant&rsquo;s Turnkey Solutions Encompass the Three Pillars of Deep Learning</h2><p>Deep learning is ideally suited to be the new interface, enabling the natural interaction between the physical and the digital worlds. The challenge with deep learning is that to provide a total solution, three key elements are required: a processor where a neural network models are run; a large set of data assets, collected and classified, which is required to create the training datasets; and a training pipeline where machine learning data models are created. &nbsp;Without any of these elements, the total solution is not possible.&nbsp;</p><p>Facilitating the adoption of deep learning as the new physical-digital interface, Syntiant has been working on solutions that cover all three of these elements. &nbsp;</p><ol><li><h3>Processor: Neural Decision Processor<em>&trade;</em></h3><br id="isPasted">Many deep learning solutions rely on traditional processor solutions that are not optimized for artificial intelligence or AI efficient. These solutions are large, consume a lot of power or are limited in their computational capabilities, making them not suitable for edge applications, where space, cost, and power consumption on a device is critically important.<br>Syntiant has developed its own AI efficient&trade; (NDP) family of solutions.<br>With native neural architecture, the NDP family offers 100x efficiency improvement and 30x increase in throughput, at 1% of the power and half the size, compared to commonly used microprocessor units (MCUs).<br>Due to the unparalleled computational power for their size, processors in the NDP family do not need to send any computational data to the cloud, eliminating bandwidth challenges and security and privacy concerns.&nbsp;</li><li><h3>Data Platform</h3><br>One of the biggest challenges in deploying artificial intelligence and deep learning solutions is the scarcity of training data. In order to circumvent this problem, Syntiant has invested in developing its own platform. The Syntiant Data Platform automates the ingestion, labelling, aligning, cleaning, and synthetic data generation to turn raw data into training data sets. In addition, the platform generates synthetic data that can be used for customization purposes in easy use cases (e.g., wake words), or increase the robustness for complicated use cases. &nbsp;</li><li><h3>Training Pipeline</h3><br>Once a large enough data set has been collected and categorized, it can be used to create training data models for the neural networks. Generating production-worthy training models is an expensive and complicated process that includes augmenting the data to include many variations, mimicking real-world scenarios. Syntiant has designed and developed its own training pipeline that has helped to increase the robustness of application-specific solutions that they offer. Furthermore, the pipeline is not limited to use with the NPD family only and may be used to create production data models for other processors.</li></ol><h2>Smart Home Security Highlights Deep Learning&rsquo;s Advantages for Edge Applications</h2><p>Taking a closer look at how deep learning is applied to improve and expand applications in a smart home security system, Syntiant not only demonstrates an exciting use case of its specially designed Neural Decision Processors, but also outlines its vision for more intuitive, natural interface at the edge of the physical and digital world.&nbsp;</p><p><a class="button-main-action" href="https://register.gotowebinar.com/recording/4111620855434586640" rel="noopener noreferrer" target="_blank">Watch the full webinar on-demand here.&nbsp;</a></p><p><strong><em>About the sponsor: Syntiant</em></strong></p><p><em>Syntiant Corp. is a leader in delivering end-to-end deep learning solutions for always-on applications by combining purpose-built silicon with an edge-optimized data platform and training pipeline. The company&rsquo;s advanced chip solutions merge deep learning with semiconductor design to produce ultra-low-power, high-performance, deep neural network processors for edge AI applications across a wide range of consumer and industrial use cases, from earbuds to automobiles. Syntiant&rsquo;s Neural Decision Processors&trade; typically offer more than 100x efficiency improvement, while providing a greater than 10x increase in throughput over current low-power MCU-based solutions, and subsequently, enabling larger networks at significantly lower power.</em></p><h2><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjUxNjU1ODkxMTg2LXN5bnRpYW50IGJvdHRvbSBiYW5uZXIuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib"></h2><p><br></p>

Deep learning increases reliability and reduces false alarms

From Window Break Alerts to Person Detection Systems: Deploying Reliable, Low Power, Edge AI for Home Security Applications

<p>This article was discussed in our <a data-saferedirecturl="https://www.google.com/url?q=https://www.wevolver.com/profile/the.next.byte&source=gmail&ust=1649206513804000&usg=AOvVaw2e8fjtjDBubEV3BD4lTqPX" href="https://www.wevolver.com/profile/the.next.byte" id="isPasted" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;</p><p><span class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable" contenteditable="false" draggable="true"><iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/e67f6081-3650-42ad-847d-ccb27822c445?dark=false" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span></p><p>The full article will continue below.</p><hr><p id="isPasted">The idea of the fully-integrated smart home, where the very surfaces themselves boast sensing, display, and control capabilities, is an alluring one which to date has not been realized by available technologies &mdash; but a woven smart display, capable of repeated bending folding and with integrated energy storage functionality, could hold the key to changing that.</p><p>Developed by a multi-organizational team led by the University of Cambridge, the novel display system&rsquo;s prototype is a 46&quot; gadget boasting full-color display capabilities alongside wireless power transmission and energy storage, touch sensing, environmental monitoring, biosensing, and photodetection &mdash; while remaining fully flexible.</p><h1>Interwoven technology</h1><p>The core concept of combining fabric-weaving manufacturing approaches with integrated technology isn&rsquo;t new, but has thus far struggled to scale beyond small-form-factor devices primarily targeting the wearable sector. This unnamed prototype, by contrast, targets scalability as a primary consideration: Its active display offers a 34&quot; diagonal, with its creators claiming devices of &ldquo;unlimited size&rdquo; could be created using existing manual or machine looms.</p><p>Featuring a conductive silver-coated polyamide thread developed in-house as a connecting material, the heart of the smart fabric is the full-color LED display panel. Dubbed a Fiber LED (F-LED) display, the output device features a matrix of 84&times;76 RGB LEDs &mdash; while a second prototype boosted the resolution to 120&times;65, the highest resolution yet achieved in fiber LED displays.</p><p><span class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable" contenteditable="false" draggable="true"><iframe src="https://www.youtube.com/embed/KP1WebOG2bM?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" allowfullscreen="" class="fr-draggable" width="640" height="360" frameborder="0" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br>The display is only part of the prototype, however: Designed as a true &ldquo;smart fabric,&rdquo; the system also includes a range of additional &ldquo;fiber devices&rdquo; designed to act as inputs: A square spiral fiber antenna, which can receive 13.56MHz signals as a mode switch and for power harvesting or communication with external devices; a fiber photodetector for environmental ultraviolet monitoring; a number of fiber touch sensors woven into the weft and warp of the fabric for simultaneous and multi-touch sensing equivalent to a traditional touchpad; a fiber temperature sensor; and a fiber biosensor, capable of monitoring and amplifying the user&rsquo;s heartbeat for monitoring and display.</p><p>The final key feature of the overall fabric system&#39;s technology bundle: Fiber supercapacitors, made from gel-electrolyte sandwiched between carbon fiber bundles, capable of storing energy within the fabric itself for later use.</p><h1>True flexibility</h1><p>Despite all these functions, the smart fabric prototype remains flexible, capable of being rolled, folded, and gently stretched without damage. In extensive experimentation, all &ldquo;F-devices&rdquo; built into the system were subjected to standardized bending tests over 1,000 cycles and a year-long operational lifespan without any notable degradation &mdash; bar the temperature sensor, which was noted to drift over time owing to moisture ingress.</p><p><span class="fr-img-caption fr-fic fr-dib" style="width: 300px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4MDUwMjI1OTU0LXdvdmVuZGlzcGxheTIuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="Diagrams showing various types of &quot;fiber devices,&quot; which are woven into a smart textile using a standard weaving loom. The finished &quot;smart textile system&quot; integrates an F-LED display, F-Touch inputs, F-RF antenna, F-Temperature sensor, F-Biosensor, F-Photodetector, and F-Energy storage system."><span class="fr-inner">The smart fabric prototype was constructed using standard loom weaving techniques, and integrates a display output and a surprisingly wide range of inputs &mdash; all created using fiber technology.<br id="isPasted"></span></span></span></p><p>To prove the concept still further, the team tested the prototype for a range of tasks &mdash; aiming for at least one useful implementation of every F-device present. Example applications included installation of the smart fabric as a UV monitor on a window, capable of triggering the movement of blinds or activation of heating or ventilation systems via touch control; display of received signal strength from the fiber antenna; live temperature graphing; heart-rate monitoring; and automatic switching between &ldquo;display mode&rdquo; and &ldquo;monitoring mode&rdquo; depending on its distance to a radio-transmitting device.</p><p>&ldquo;Our approach is built on the convergence of micro and nanotechnology, advanced displays, sensors, energy and technical textile manufacturing,&rdquo; says Professor Jong min Kim, project co-lead, in a write-up of the work <a href="https://www.wevolver.com/article/scientists-develop-fully-woven-smart-display/" target="_blank">published here on Wevolver</a>. &ldquo;This is a step towards the full exploitation of sustainable, convenient e-fibers and e-textiles in daily applications. And it&rsquo;s only the beginning.&rdquo;</p><p><span class="fr-img-caption fr-fic fr-dib" style="width: 300px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ4MDUwMjMzNDQ5LXdvdmVuZGlzcGxheTMuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="Three images of the smart textile display system being used to graph temperature changes recorded by the F-Temperature sensor. An arrow goes from &quot;heating&quot; to &quot;cooling&quot; left-to-right to demonstrate the change being measured."><span class="fr-inner">The integrated fiber devices can perform a range of tasks, from environmental monitoring to touch detection &mdash; and even track your heart rate.</span></span></span></p><p>&ldquo;By integrating fiber-based electronics, photonic, sensing and energy functionalities, we can achieve a whole new class of smart devices and systems,&rdquo; adds fellow co-lead &nbsp;Dr Luigi Occhipinti. &ldquo;By unleashing the full potential of textile manufacturing, we could soon see smart and energy-autonomous Internet of Things devices that are seamlessly integrated into everyday objects and many other sector applications.&rdquo;</p><p>The team&rsquo;s work has been published in the journal <cite><a href="https://www.nature.com/articles/s41467-022-28459-6" target="_blank">Nature Communications</a></cite> under open-access terms; the codes used in the project are available <a href="https://www.repository.cam.ac.uk/handle/1810/331012" target="_blank">via the University of Cambridge&rsquo;s Apollo system</a> upon application.</p><h1>Reference</h1><p>Hyung Woo Choi, Dong-Wook Shin, Jiajie Yang, Sanghyo Lee, C&aacute;tia Figueiredo, Stefano Sinopoli, Kay Ullrich, Petar Jovančić, Alessio Marrani, Roberto Moment&egrave;, Jo&atilde;o Gomes, Rita Branquinho, Umberto Emanuele, Hanleem Lee, Sang Yun Bang, Sung-Min Jung, Soo Deok Han, Shijie Zhan, William Harden-Chaters, Yo-Han Suh, Xiang-Bing Fan, Tae Hoon Lee, Mohamed Chowdhury, Youngjin Choi, Salvatore Nicotera, Andrea Torchia, Francesc Ma&ntilde;osa Moncunill, Virginia Garcia Candel, Nelson Dur&atilde;es, Kiseok Chang, Sunghee Cho, Chul-Hong Kim, Marcel Lucassen, Ahmed Nejim, David Jim&eacute;nez, Martijn Springer, Young-Woo Lee, SeungNam Cha, Jung Inn Sohn, Rui Igreja, Kyungmin Song, Pedro Barquinha, Rodrigo Martins, Gehan A. J. Amaratunga, Luigi G. Occhipinti, Manish Chhowalla, and Jong Min Kim: <cite>Smart textile lighting/display system with multifunctional fibre devices for large scale smart home and IoT applications, Nature Communications 13</cite>. DOI <a href="https://doi.org/10.1038/s41467-022-28459-6" target="_blank">10.1038/s41467-022-28459-6</a>.</p>

A prototype smart display, fully reproducible using industry-standard looms, is shown here being folded and rolled while retaining its performance.

Featuring "fiber devices" including a large-format display, temperature and ultraviolet sensors, a touch-sensitive input matrix, and even a heart-rate monitor, this foldable fabric is being positioned as a breakthrough for smart homes and the IoT.

A flexible, foldable, highly-integrated "smart fabric" could herald the future of the cuddlier Internet of Things

<p id="isPasted">Real-time occupancy monitoring of the comings and goings inside a warehouse, conference room, or corridor yields valuable data. That data can be sent to the Cloud for deeper analysis and strategic decision-making on occupancy issues such as enhanced building security, personnel safety monitoring, and sustainable lighting and HVAC use.</p><h2>Better productivity and planning</h2><p>System managers can maximize space usage and boost productivity by monitoring building occupancy. For example, a wireless occupancy sensor solution could instantly notify whether a meeting room is currently occupied or how many people on average use a particular room.</p><p>Occupancy detection also has a role to play in maintaining health and safety. For example, the technology makes it much easier to implement social distancing policies that will help keep an endemic variant of COVID-19 and other endemic diseases such as influenza at bay.</p><p>Wireless occupancy detection can also replace traditional lighting controls in a smart building or home. Improvements in efficiency from automated lighting can be dramatic. Such systems can significantly reduce energy use in commercial buildings, where lighting constitutes some 26 percent of total electricity consumption. According to data from the U.S. Department of Energy, installing occupancy-based sensor lighting controls can lead to energy savings of ten percent in an open-plan office, 45 percent in a warehouse, and as high as 60 percent in a restroom.</p><p>Employing occupancy sensors linked to HVAC controls can lead to similar energy savings. The sensors can adjust temperature settings, turn down airflows, or even turn the HVAC off depending on who's around.</p><h2>Motion sensor types</h2><p>Wireless occupancy sensors commonly use infrared (IR) light and microwaves, among other techniques, to detect the presence of people even when they're stationary.</p><p>The passive IR (PIR) sensor is the more common type due to its simplicity and relatively low cost. It is triggered by IR level change, like from a warm object such as a person. PIR sensors feature low energy consumption—the sensor's passive operation requires very little power compared to other motion detection systems—making a good alternative in an application where extended battery life is critical. Some downsides to PIR technology are that it struggles to detect tiny movements, must have direct line-of-sight with the moving object to operate, has limited range and restricted coverage area.</p><p>Microwave sensors address the weaknesses of PIR because they can cover wide areas, feature good range, and don't require line-of-sight with the moving object. The downsides are cost, and most significantly, power consumption. The units must constantly emit a microwave signal, which requires continuous power draw.</p><p>Hybrid or dual-technology sensors incorporating PIR and microwave in a single device combine the advantages of each technology for a high-performance motion detector system with a very low false detection rate. The downside is cost.</p><h2>Easy-fit occupancy detection</h2><p>Brossard, Canada-based <a href="https://www.nordicsemi.com/News/2021/09/I-SYST-module-employs-nRF52832-SoC?utm_campaign=2021%20wevolver" rel="noopener noreferrer" target="_blank">I-SYST</a>, has developed the BLUEPYRO-M3225, a module providing plug-and-play motion/proximity detection capability, to support various wireless room occupancy detection applications. The product has been designed to help inexperienced PIR users quickly set up a wireless room occupancy detection system. It works in the home/building automation range, such as lighting control, security systems, smart thermostats, and in wildlife motion detection photography applications.</p><p>The I-SYST module integrates Nordic's nRF52832 SoC to deliver the processing power required for such applications. BLUEPYRO-M3225 features the Excelitas Technologies DigiPyro PYD2592, a dual-element PIR sensor with built-in signal processing, digital output, and wake-up/sleep mode functionality. The PIR sensor integration in the module enables a wireless solution with low electromagnetic interference (EMI) characteristics. The PIR sensor's wake-up feature is essential for battery-operated applications because it limits power use until a motion event is detected.</p><p>The wireless occupancy sensor market is on the move, with companies and individuals reaping the rewards of enhanced detection capability. For example, The Business Times reports that in Schneider Electric's offices in Kallang, Singapore, over a thousand sensors across nine floors track the occupancy of workstations and meeting rooms in near real-time. The data helps the company tailor lighting and HVAC according to attendance.&nbsp;</p><hr><p>This article was first published on Nordic's&nbsp;<a href="https://blog.nordicsemi.com/getconnected" target="_blank" rel="nofollow" id="isPasted"></a><a href="https://blog.nordicsemi.com/getconnected?utm_campaign=2021%20wevolver" rel="nofollow" target="_blank">Get Connected Blog</a>. </p>

Real-time occupancy monitoring of the comings and goings inside a warehouse, conference room, or corridor yields valuable data.

Wireless occupancy detection technology aids productivity and sustainability

<p><em id="isPasted">Together with&nbsp;</em><a href="https://www.wevolver.com/profile/digi-key.electronics" rel="noopener noreferrer" target="_blank"><em>Digi-Key</em></a><em>, a <em>distributor of electronic components,</em> we are creating&nbsp;</em><a href="https://www.wevolver.com/article/the-tech-foundation-of-smart-city-infrastructure" rel="noopener noreferrer" target="_blank"><em>a series of articles</em></a><em>&nbsp;about the technologies that make IoT possible. &nbsp;This second article examines the use of machine learning to power scenes in smart homes. Future articles dive into IoT security and connected transportation.&nbsp;</em></p><p>For over two decades, smart homes and home automation applications have advanced at a rapid pace. Early smart homes comprised a limited number of connected devices and offered very basic automation functionalities, which were typically limited to controlling the status of smart devices. During the past decade, home automation functionalities have proliferated and evolved in terms of intelligence and sophistication. Specifically, smart homes platforms like Amazon Echo, Google Home and Apple&rsquo;s Home Pod enable integrated and intelligent control of a larger number of devices. The latter can be configured in many ways to match the end-users&rsquo; preferences and needs. &nbsp; &nbsp;&nbsp;</p><h2>Introducing Smart Home Scenes</h2><p>The multitude of home automation devices and functionalities in modern smart homes has given rise to the concept of &ldquo;scenes&rdquo;. Scenes enable smart home users to control multiple devices based on one or more scripts of well-defined actions. The latter are scheduled and executed in-line with the end-users&rsquo; preferences. &nbsp;In practice, scenes consist of triggers and actions.&nbsp;</p><p>Triggers are events that initiate configuration and control actions. For example, configuration actions can be triggered when the value of a sensor exceeds a threshold or based on the manual push of a button. Actions alter the status of one or more devices, which subsequently changes the state of the smart home. &nbsp;The triggers and actions that comprise a scene are stored in the smart home platform as a configuration option. This option can be conveniently activated or deactivated at the end-user&rsquo;s will. Smart home users can therefore configure multiple scenes and use them at different times.</p><p dir="ltr">Overall, scenes facilitate homeowners to control their smart devices flexibly and automatically. Using scenes, homeowners save precious time. Specifically, they no longer need to remember the different configuration options of their devices, allowing them to spend less or no time in implementing a series of configuration and control actions to ensure that their home environment matches their preferences. &nbsp;Furthermore, scenes enable homeowners to control their home using their most preferred modality including remote controls, touch-panels and smartphone apps.</p><h2>Prominent Scenes Examples &nbsp;</h2><p>Some of the most popular examples of smart home scenes include:</p><ul><li dir="ltr"><p dir="ltr">The Morning Scene:&nbsp;This is typically a scene that configures a smart home to the owner&rsquo;s desired morning state. It typically involves switching on certain lights, opening curtains, turning on the TV or radio in some rooms (e.g., the bathroom), and configuring certain appliances (e.g., toasters, boilers) to the desired state. Different instances of the morning scene can be implemented for different members of the household. For instance, different morning scenes can be implemented in the various bedrooms or bathrooms of the smart home.</p></li><li dir="ltr"><p dir="ltr">The Night Scene: This scene reverses the state of the morning scene and prepares the home for the night. For instance, some lights are switched off, the radio and the TV are turned off, and the home is locked up and secured.</p></li><li dir="ltr"><p dir="ltr">The Away Scene: In this case, the house is configured to the state preferred by homeowners when they are not present. As a prominent example, interior lights and media devices are turned off, shades are closed, exterior lights are switched on, and the alarm is set.&nbsp;</p></li><li dir="ltr"><p dir="ltr">The In-Home Scene:&nbsp;This configures the home to the users&rsquo; desired state when one or more household members are in the house. The configuration of the scene can be personalized to the preferences of each individual member. For instance, a personalized configuration can define specific states for the lighting of the living room and the office, the ambient temperature of certain rooms, as well as the status of the TV and radio devices.</p></li><li dir="ltr"><p dir="ltr">The Party Scene: &nbsp;This is about preparing the home for a social event like a party. Among other things, it can configure the lighting, the shades, the type and volume of the music, and the temperature towards creating a pleasant and effective environment for the event. The selected configuration can be activated with a click of a button on a remote control or smartphone app. &nbsp;</p></li></ul><p><span class="fr-video fr-deletable fr-fvc fr-dvb fr-draggable" contenteditable="false" draggable="true"><iframe src="https://www.youtube.com/embed/O8PtChkkzuU?&wmode=opaque&rel=0&enablejsapi=1&origin=https://www.wevolver.com" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 740px; height: 426px;" data-gtm-yt-inspected-10="true" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe></span><br></p><h2 dir="ltr">Smart Home Scenes: Technology Enablers and Trends</h2><p dir="ltr">The implementation and deployment scenes are enabled by cutting-edge smart home technologies such as intelligent sensors, cloud computing, and the Internet of Things (IoT). In particular:</p><ul><li dir="ltr">Intelligent Sensors and Actuators: Scenes leverage intelligent semiconductors and microsystems, which are configured remotely based on popular protocols like Bluetooth, WiFi, Zigbee, and KNX. Intelligent semiconductors are of two main types: Sensors that perceive the smart-home environment (e.g., a room&rsquo;s occupancy patterns) and Actuators that implement automatic control functionalities (e.g., light control).</li><li dir="ltr">IoT Controllers: Most scenes are configured, stored, deployed, and executed by IoT controllers i.e., gateway devices that control sensors and actuators from a single-entry point. IoT controllers support one or more networking protocols, which facilitate their seamless communication with sensors and actuators.&nbsp;</li><li dir="ltr">Cloud Computing: Modern smart home platforms and their IoT controllers are integrated with cloud computing infrastructures. Cloud integration enables smart home applications to benefit from the scalability, capacity, elasticity, and quality of service of cloud computing. For instance, the cloud facilitates the collection, management, and analysis of large volumes of data about the activity of the inhabitants. Likewise, cloud computing enables smart home applications to access storage and computing resources in flexible, scalable, and cost-effective ways.</li><li dir="ltr">Edge Computing: In recent years, there is a shift of smart home data from the cloud to the edge of the network, i.e., close to end-users. Many data processing and data analytics applications are deployed close to the end-users. This reduces application latency as processing takes place in the local network. &nbsp;Moreover, it economizes network bandwidth and boosts data protection as most data need not travel to the cloud. In most cases, edge computing is deployed in conjunction with cloud computing, i.e., real-time functionalities are deployed at the edge, while functionalities that ask for many data points and heavier processing are implemented in the cloud.</li></ul><p>These technologies are the main technology enablers of smart home applications and scenes. Their evolution is driving improvements in automation, intelligence, and sustainability. Some of the top trends include: &nbsp;</p><ul><li dir="ltr">Tiny Sensors: Sensors are gradually shrinking in size, which increases their versatility and pervasiveness. In this direction, modern sensing systems come with zero-touch configuration capabilities as well. Overall, the trend is towards pervasively deploying sensors without substantial effort for setting them up and operating them. &nbsp; &nbsp; &nbsp;</li><li dir="ltr">Energy Efficiency: Nowadays, consumers and enterprises are concerned with improving the environmental performance of their activities. This trend is extending to smart home applications, which are designed and engineered towards reducing CO2 emissions and optimizing environmental performance. For example, occupancy monitoring functionalities are increasingly used to optimize HVAC (Heating Ventilation and Air Conditioning) systems emissions. Likewise, smart homes are increasingly deploying energy-efficient sensors that live longer and exhibit optimal environmental performance.&nbsp;</li><li dir="ltr">Cyber-Physical Systems and Robotic Innovations: Future smart homes will benefit from Cyber-Physical Systems (CPS), i.e., specialized IoT devices that comprise both a cyber and a physical part. They will comprise various robotics devices and will be used to provide assistive functions to the tenants. Prominent examples include socially assistive robots, drones for parcel picking, as well as smart actuators that react to water leakages. &nbsp;</li><li dir="ltr">Strong Cybersecurity and Reliability: As smart home scenes evolve in number and functional sophistication, there will be a need for stronger cyber-security and reliability. The latter must be offered in a user-friendly way that enables even the most na&iuml;ve users to configure and deploy security functions. &nbsp;</li><li dir="ltr">Increased Automation and Real-Time Operations: Scenes represent an important step in increasing smart home automation. In the coming years, scenes will become even more automated and intelligent. Moreover, they will comprise an increased number of real-time functions such as real-time monitoring of the status of rooms and real-time actuation in emergency cases (e.g., switching off gas or electricity upon the detection of earthquake signals). &nbsp;</li></ul><p><span class="fr-img-caption fr-fic fr-dib" style="width: 766px;"><span class="fr-img-wrap"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQyMTU0NDExNDUyLW5lc3QtdGhlcm1vc3RhdC1lLWhlcm8uanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 788px;" class="fr-fic fr-dib"><span class="fr-inner" spellcheck="false">Sensors are becoming smaller and smarter: Image credit: Nest.</span></span></span></p><p>Nevertheless, the most disruptive innovations in the areas of smart home scenes will come from the deployment of Artificial Intelligence (AI), notably from Machine Learning (ML) which represents the most popular class of AI techniques.&nbsp;</p><h2>Smarter Scenes with Machine Learning and Artificial Intelligence</h2><p>The blending of ML functions into smart home scenes is the next evolutionary step in home automation. Most of the state-of-the-art scenes are based on simple if-then-else rules over triggers and actions. This deterministic logic boosts automation, yet it provides very limited intelligence. &nbsp;For example, simple rules do not consider the evolution of users&rsquo; habits and behaviors. ML alleviates these limitations by enabling scenes that learn the residents&rsquo; behavioral patterns and use them to optimize smart home operations. In this direction, ML algorithms can be trained using past data about the users&rsquo; activities in their home environment.&nbsp;</p><p>Leveraging such algorithms, scenes can be enhanced in terms of dynamicity and intelligence. Specifically, rather than always applying the same configuration actions during a given time interval, ML-enabled scenes can dynamically change the actions in-line with the evolution of the residents&rsquo; behavior. Moreover, the use of ML can lift the limitations of choosing between a few pre-configured scenes for different times of the day (e.g., morning, afternoon, evening). This is because ML-based scenes can continually and dynamically adapt to the users&rsquo; habits and behavior, even when the latter changes several times during the day. &nbsp; &nbsp;&nbsp;</p><h3>Prominent examples of user-centric ML-based scenes include:</h3><ul><li dir="ltr">Personalized Automated Home Ambience &ndash; Learning Users&rsquo; Preferences: In this case, the scenes automatically learn the users&rsquo; preferences about the ambient environment, i.e., about the lighting system, the operation of the air-conditioning, the configuration of the music player, the personal assistance services, the shades, the doors and more. Accordingly, they dynamically personalize the ambient environment to the users&rsquo; preferences.</li><li dir="ltr">Occupancy Monitoring for Cost and Carbon Footprint Reduction: This type of scene leverages machine learning and computer vision recognition systems to extract occupancy patterns in the different rooms of the residential environment. Leveraging the identified patterns, the scenes configure the home&rsquo;s operations (e.g., lighting, air conditioning) in ways that minimize energy costs and optimize CO2 emissions.</li><li dir="ltr">Intelligent Recommendations of &ldquo;Optimal&rdquo; Scenes &ndash; Learning Scenes Dynamically: Leveraging past data about the users&rsquo; in-home behavior and the operation of the different devices, it is possible to construct scenes (i.e., smart home configurations) that economize on costs and optimize environmental performance. These configurations can be recommended to the end-users. Following the end-users approval, they can be stored and deployed in the smart home. In this case, ML enables the dynamic construction of &ldquo;optimal&rdquo; scenes rather than relying on pre-configured ones. &nbsp;</li></ul><h2>Summary</h2><p>The implementation of ML-based scenes hinges on the collection and processing of large volumes of data about operations, triggers, and actions, including users&rsquo; activities and behaviors within the residency. These data can enable the training of different types of ML algorithms, including traditional ML techniques (e.g., Decision Trees, Random Forests and SVM (Support Vector Machines)) and Deep Learning algorithms (e.g., Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN)). In cases where very large amounts of past data are available, ML techniques provide better performance and accuracy in understanding behavioral patterns and tailoring scenes&rsquo; configurations accordingly.</p><p>Scenes are nowadays an integral element of smart home intelligence. They boost home automation in ways that provide convenience to end-users and help them apply their desired configuration actions faster. Nevertheless, state-of-the-art scenes are quite simple and static. In this context, the emerging wave of ML-enabled scenes are set to disrupt the smart home applications landscape by enabling the development of more dynamic and intelligent scenes.&nbsp;</p><p>ML is the next evolutionary step in smart home scenes. It will act as a catalyst for realizing the shift from existing rule-based scenes (Scenes 1.0) to the next generation of dynamic and highly personalized scenes (Scenes 2.0). Smart home deployers must therefore plan for integrating ML functions into their solutions to provide consumers with new levels of comfort and personalization. &nbsp;</p><p dir="ltr" id="isPasted">Article one <a href="https://www.wevolver.com/article/the-tech-foundation-of-smart-city-infrastructure" rel="noopener noreferrer" target="_blank">set the foundations of a smart city infrastructure.</a></p><p dir="ltr">Article two looked into <a href="https://www.wevolver.com/article/what-makes-a-smart-home-smart-a-guide-to-protocols-and-applications" rel="noopener noreferrer" target="_blank">what makes a Smart home, smart.</a></p><p dir="ltr">Article three explored how <a href="https://www.wevolver.com/article/machine-learning-powered-home-scenes-a-blueprint-for-intelligent-home-automation" rel="noopener noreferrer" target="_blank">Smart ML enables scenes for new seamless ways of interacting with smart home devices.</a></p><p dir="ltr">Article four explained <a href="https://www.wevolver.com/article/redefining-speed-and-facilitating-transformation-in-urban-mobility" rel="noopener noreferrer" target="_blank">how 5G and 6G will assist in delivering smarter communication.</a></p><p dir="ltr">Article five discussed about <a href="https://www.wevolver.com/article/smart-home-security-security-and-vulnerabilities" rel="noopener noreferrer" target="_blank">Smart Home security.</a></p><h2 dir="ltr" id="isPasted"><em>About the sponsor: Digi-Key</em></h2><p><a href="https://www.wevolver.com/profile/digi-key.electronics" rel="noopener noreferrer" target="_blank"><em>Digi-Key</em></a><em>&nbsp;is one of the fastest-growing distributors of electronic components in the world. Since its founding in 1972, Digi-Key has been committed to offering the broadest selection of in-stock electronic components, as well as providing the best service possible to its customers, aiding engineers through the entire design process, from Prototype to Production&reg;.&nbsp;</em><em><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQyMTUwMzE0NzcwLWJhbm5lciBib3R0b20uanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib"></em>&nbsp;</p>

smart home

ORGANIZATIONS. SHAPING THE INDUSTRY.

Qorvo

Latest Posts

From Window Break Alerts to Person Detection Systems: Deploying Reliable, Low Power, Edge AI for Home Security Applications

A flexible, foldable, highly-integrated "smart fabric" could herald the future of the cuddlier Internet of Things

Wireless occupancy detection technology aids productivity and sustainability

Machine Learning Powered Home Scenes: A Blueprint for Intelligent Home Automation